INDEXES AND BOUNDARIES FOR QUANTITATIVE SIGNIFICANCE IN STATISTICAL DECISIONS
INDEXES AND BOUNDARIES FOR QUANTITATIVE SIGNIFICANCE IN STATISTICAL DECISIONS
复制标题
DOI：
10.1016/0895-4356(90)90093-5
复制
发表时间：
1990-01-01
影响因子：
7.2
通讯作者：
FEINSTEIN, AR
中科院分区：
文献类型：
--
作者：
BURNAND, B;KERNAN, WN;FEINSTEIN, AR
代表“数量上显著”或“实质上令人印象深刻”的区别的delta的界限尚未确定，类似于“统计显著性”的随机或概率部分的alpha的界限，通常设定为0.05。 为了确定“定量”决策的边界，我们回顾了三种普通医学期刊上的相关文章。 对于两个平均值的对比、两个比率的对比或相关系数，我们注意到研究者关于随机显著性的决定，以P值或置信区间表示，以及关于定量显著性的决定，通过解释性的评论表明。令人印象深刻的和不令人印象深刻的区别之间的界限最好由比或等于比的比率形成。在546次比较中，对于较小到较大的平均值，标准化增量大于或等于0.28，在392次两种比率的比较中，比值比大于或等于2.2;在154个相关系数中，r值大于或等于0.32。 还确定了“实质上”和“高度”显著性定量区分的其他界限。尽管建议的界限应保持灵活性，但当必须在研究完成前选择δ值用于计算样本量时，决定“定量显著性”的指数和界限特别有用，当完成的研究的“统计意义”被评估为定量和随机成分时。
Boundaries for delta, representing a "quantitatively significant" or "substantively impressive" distinction, have not been established, analogous to the boundary of alpha, usually set at 0.05, for the stochastic or probabilistic component of "statistical significance". To determine what boundaries are being used for the "quantitative" decisions, we reviewed pertinent articles in three general medical journals. For each contrast of two means, contrast of two rates, or correlation coefficient, we noted the investigators' decisions about stochastic significance, stated in P values or confidence intervals, and about quantitative significance, indicated by interpretive comments.The boundaries between impressive and unimpressive distinctions were best formed by a ratio of greater-than-or-equal-to-1.2 for the smaller to the larger mean in 546 comparisons, by a standardized increment of greater-than-or-equal-to-0.28 and odds ratio of greater-than-or-equal-to-2.2 in 392 comparisons of two rates; and by an r value of greater-than-or-equal-to-0.32 in 154 correlation coefficients. Additional boundaries were also identified for "substantially" and "highly" significant quantitative distinctions.Although the proposed boundaries should be kept flexible, indexes and boundaries for decisions about "quantitative significance" are particularly useful when a value of delta must be chosen for calculating sample size before the research is done, and when the "statistical significance" of completed research is appraised for its quantitative as well as stochastic components.